Related Experiment Video
Updated: May 5, 2026
06:49
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
Published on: December 11, 2015
8.8K
A Robust Cross-Platform Solution With the Sense2Quit System to Enhance Smoking Gesture Recognition: Model Development
Anarghya Das1, Juntao Feng1, Maeve Brin2
1Department of Computer Science & Engineering, University at Buffalo, The State University of New York, Buffalo, NY, United States.
Journal of Medical Internet Research
|May 20, 2025
Summary
Sense2Quit uses smartwatches and AI to accurately detect smoking gestures, offering real-time interventions for people with HIV quitting smoking. This technology reduces false positives from similar hand movements, aiding cessation efforts.
Area of Science:
- Digital Health
- Artificial Intelligence
- Mobile Health Interventions
Background:
- Smoking is a major cause of preventable death, with higher rates and health risks among people with HIV.
- Existing smoking cessation tools lack real-time intervention capabilities.
- Technological advancements are needed to support smoking cessation in vulnerable populations.
Purpose of the Study:
- To develop an accurate AI-powered mobile app for smoking cessation using smartwatch data.
- To differentiate smoking gestures from confounding hand-to-mouth activities, minimizing false positives.
- To ensure cross-platform compatibility (Android/iOS) and real-time monitoring.
Main Methods:
- Developed a 'confounding resilient smoking model' trained to distinguish smoking from 15 other gestures.
- Recruited 30 participants (people with HIV who smoke) to perform various hand-to-mouth activities.
- Utilized the Flutter framework for cross-platform app development with real-time smartwatch synchronization.
Main Results:
- The AI model achieved a 97.52% F1-score in accurately detecting smoking gestures.
- The system successfully differentiated smoking from 15 confounding daily activities.
- The cross-platform app showed consistent performance and user experience across Android and iOS devices.
Conclusions:
- Sense2Quit significantly advances smoking cessation technology for people with HIV.
- Innovations in gesture recognition and cross-platform optimization enable accurate, real-time interventions.
- The app is a valuable tool for supporting sustained smoking cessation.
Related Concept Videos
02:43Mouse Models of Cancer Study
4.7K
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
4.7K
01:16Crossover Experiments
3.4K
Crossover experiments, also called the repeated-measurements design, is a study design in which all experimental units are exposed to all treatments in different periods. Crossover experiments are generally used in psychology, the pharmaceutical industry, agriculture, and medicine.
Crossover designs are performed even with smaller sample sizes since the samples can act as their controls. These are better than simple randomized trials since patients are exposed to all the treatments.
Crossover designs are performed even with smaller sample sizes since the samples can act as their controls. These are better than simple randomized trials since patients are exposed to all the treatments.
3.4K